321w12p1 - Outliers Outliers or influential observations...

Info iconThis preview shows pages 1–4. Sign up to view the full content.

View Full Document Right Arrow Icon
Outliers Outliers or influential observations can arise due to errors in the data, or because some of the data may be generated by a different model than the other data Outliers – observations that are substantially different from the majority of the data. OLS setimates can change dramatically when outliers are dropped from the data set.
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Some outliers occur because of a mistake So it is a good idea to look at summary statistics for your data set: maximum, minimum as well as means, to identify possible mistakes. An obvious data error should be dropped.
Background image of page 2
However, outliers can also occur if one or several members of the population behave differently from the rest of the population. You do not necessarily wish to drop these data. Outlying observations can increase the variation in the explanatory variables. More importantly, they can indicate differences in behaviour that should be further investigated If several outlying observations substantially change your results, you should report the OLS estimates with and without these observations.
Background image of page 3

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Image of page 4
This is the end of the preview. Sign up to access the rest of the document.

Page1 / 12

321w12p1 - Outliers Outliers or influential observations...

This preview shows document pages 1 - 4. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online